Title :
Object ranging and tracking for aircraft landing system
Author :
Mohan, K. K. Navya ; Wilscy, M.
Author_Institution :
Dept. of Comput. Sci., Univ. Of Kerala, Thiruvananthapuram, India
Abstract :
We present a novel approach for combined object detection, ranging and tracking that can be used during the landing of aircraft. The objective is to alert pilots if their aircraft is in immediate danger of flying into the ground or an obstacle. This is to avoid accidents or any other calamity caused by a moving or stationary object by detecting the object prior to approaching the same. The input to the system is a real-time video sequence recorded by a stereoscopic camera mounted on the moving aircraft. The system detects the stationary and moving objects and tracks those in the consecutive frames of the video sequence. The tracking is carried out using Particle filter and the distance to the tracked objects is continuously monitored. The stationary objects are detected using a combination of Watershed segmentation and Otsu thresholding and the distance to the detected objects are estimated. The objects are classified based on their presence in either of the two proximity warning zones such as danger zone or safe zone. Visual highlighting is made according to the distance of the object from the aircraft.
Keywords :
aerospace engineering; aerospace safety; aircraft; image classification; image segmentation; image sequences; object detection; object tracking; particle filtering (numerical methods); stereo image processing; video signal processing; Otsu thresholding; accident avoidance; aircraft landing system; object classification; object detection; object ranging; object tracking; particle filter; stereoscopic camera; tracked object distance; video sequence; visual highlighting; watershed segmentation; Image color analysis; Image segmentation; Ions; Stereo image processing; Tracking; Object Detection; Object Ranging; Otsu thresholding; Particle filter tracking; Stereoscopic images; Watershed Segmentation;
Conference_Titel :
Signal Processing Image Processing & Pattern Recognition (ICSIPR), 2013 International Conference on
Conference_Location :
Coimbatore
Print_ISBN :
978-1-4673-4861-4
DOI :
10.1109/ICSIPR.2013.6497939